PENINGKATAN AKURASI IMPUTASI DATA YANG HILANG PADA DATA DERET WAKTU MULTIVARIAT MENGGUNAKAN DEEP LEARNING

YULTRIYEN, YULTRIYEN and Tutuko, Bambang and firdaus, firdaus (2024) PENINGKATAN AKURASI IMPUTASI DATA YANG HILANG PADA DATA DERET WAKTU MULTIVARIAT MENGGUNAKAN DEEP LEARNING. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011282025075.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011282025075_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011282025075_0012016003_0221017801_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011282025075_0012016003_0221017801_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (818kB) | Request a copy
	Text RAMA_56201_09011282025075_0012016003_0221017801_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (911kB) | Request a copy
	Text RAMA_56201_09011282025075_0012016003_0221017801_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011282025075_0012016003_0221017801_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (467kB) | Request a copy
	Text RAMA_56201_09011282025075_0012016003_0221017801_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (366kB) | Request a copy
	Text RAMA_56201_09011282025075_0012016003_0221017801_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (265kB) | Request a copy

Abstract

Missing data is a common and complex issue in the industrial world, making data processing more challenging. Imputation methods, whether conventional or using neural networks, are employed to address this issue by estimating or computing the missing values. Deep learning is chosen for its ability to unearth hidden information within data, significantly enhancing the data imputation process. This study utilizes three deep learning methods: LL-CNN, EDR-CNN, and MIRNet. The performance of these methods is evaluated based on root mean squared error (RMSE), mean absolute error (MAE), and R-squared (R²) on eight different datasets: MIMIC-IV, MIMIC III, Beijing Multi-Site Air Quality, Air Quality Italy, Air Quality India, US Pollution, Beijing PM2.5, and Guangzhou. The results of the study show that EDR-CNN provides the best performance across all eight datasets.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Imputasi data, data yang hilang, LL-CNN, EDR-CNN, MIRNet.
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Yultriyen Yultriyen
Date Deposited:	28 Aug 2024 03:55
Last Modified:	28 Aug 2024 03:55
URI:	http://repository.unsri.ac.id/id/eprint/155915

Actions (login required)

View Item